0
$\begingroup$

I recently found an interesting paper on what it really means for a recurrent neural network (RNN) to be deep here. Depth can be added in several different ways (state to state, input to state, etc.) and the authors give several interesting architectures. I've been looking (via Google) for packages that support creating these kinds of structures in an intuitive way that is quick/easy to implement but I have come up empty thus far. Does anyone know of a freely available package that supports the various structures detailed in the reference paper?

Improve this question
$\endgroup$
2
  • $\begingroup$ R can run TensorFlow and Keras, though their installations are not as simple as the usual install.packages. Would those be enough? $\endgroup$
    – Dave
    Commented Aug 19 at 14:17
  • $\begingroup$ Thank you for the comment. I currently run TensorFlow and Keras in R. As you've implied I'd probably be better off using python. I have not seen a straightforward way to implement the interesting architectures mentioned in the paper using Keras though. $\endgroup$
    – noNameTed
    Commented Aug 20 at 15:10

1 Answer 1

Reset to default
0
$\begingroup$

In order to bring more focus to your search, I advise you to check CRAN Task View website with the task "Machine and Statistical Learning", for instance. CRAN is the official R packages repository, therefore all these libraries are freely available and easy to use in R.

This page gives a detailed overview of many available packages with explainations about the usage. For instance, here is a package you may find useful: https://cran.r-project.org/web/packages/deepNN/index.html.

Hope this helps!

Improve this answer
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.